Skip to main content
NexoraLaunch home

Build log live

Ficelle logo

LLM APIs & models

Ficelle

OpenAI-compatible router that puts free LLM models from 13 providers behind one endpoint with automatic failover

  • 0community votes
  • 0DR by Ahrefs no change since last check

Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 25 Oct 2026.

Ficelle routes requests to free LLM models across 13 providers with automatic failover and zero paid model spending enforced in code.

What it is

Screenshot of the Ficelle homepage
What ficelle.ai looks like

Ficelle is an OpenAI-compatible router that puts free LLM models from 13 providers behind one endpoint. When one model rate-limits or fails, the router automatically tries the next eligible free model and reroutes the request in milliseconds. The core router is free and includes strict-zero routing with OpenRouter and Nous reference providers. Ficelle tests whether each model handles tool calls, JSON and vision before routing requests, ranking working models by speed and reliability. Paid fallback is hardcoded off in the code, so routed requests cannot accidentally bill you. The router runs locally on your machine with your API keys staying local, and prompts go directly to the provider without a middleman proxy.

Pro adds a maintained provider pool, model fusion, prompt compression and one-command updates. In a 76-task benchmark against gpt-5, free routing was quality-safe for classification (100%), JSON extraction (95%) and reasoning (94%), though paid models still perform better for polished long-form writing.

Systems

  • Automatic failover across 13 free LLM providers
  • OpenAI-compatible API endpoint
  • Model capability testing for tools, JSON and vision
  • Hardcoded zero paid model fallback
  • Local router with keys staying on your machine
  • Model fusion and answer synthesis in Pro
  • Custom virtual model profiles in Pro
  • Native prompt compression to reduce tokens
  • Automatic model cooling and recovery probing
  • Support for Cursor, Continue, Open WebUI, LangChain and Claude Code

Pricing

Pricing model: Freemium

Free: open core under BSL 1.1, no account or card required. Pro: 12 € monthly (or 9.08 € per month billed annually at 109 €/yr), or 199 € for Lifetime license (one payment, no renewals, limited to first 200). 14-day free trial for Pro requires a card.

Follow status. Log in to follow Ficelle's status

Want to see what Ficelle does next? Follow them for milestones, new products and stories by email.

Ficelle metrics

Signal readout for ficelle.ai: Ahrefs Domain Rating and Majestic link signals, arrows for the change since the last scan.

  • 0 Domain Rating no change since last check
  • 0 Trust Flow no change since last check
  • 12 Citation Flow no change since last check
  • 1 Referring domains no change since last check
  • 2 External backlinks no change since last check

Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 25 Oct 2026. Majestic signal 25 Oct 2026, signal shifted 25 Oct 2026. Link signals from Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.

Ficelle domain signal

Show the signal details

Public RDAP record, last read 12 Nov 2026, 21:11 UTC.

  • Domain age 3 months
  • Registered
  • Expires
  • Registrar InternetX
  • DNSSEC Not signed

Full signal for ficelle.ai

Ficelle post-launch signal

The record for Ficelle after its launch on Nexora Launch (25 October 2026), from the readings we keep.

  • 0 Domain Rating (Ahrefs) no change since launch
    at launch: 0 (25 Oct 2026); latest: 12 Nov 2026
  • 0 Trust Flow (Majestic)
    first measured 25 Oct 2026
  • 1 Referring domains (Majestic)
    first measured 25 Oct 2026

Day 18 since launch. Next receipt: day 30, 24 Nov 2026. A change here is a reading, not a claim about its cause; lots of things move these figures. Anything we do not measure is not shown.

Biggest gains on Nexora Launch

Got a launch coming up?

Plan your launch with our free playbook, from preparing your listing to choosing more launch directories.

See the launch playbook

Quick answers

Is it really free?
The open core is free under BSL 1.1 and includes strict-zero routing, OpenRouter and Nous reference providers, and the one-command installer. Pro adds the maintained provider pool, model fusion, prompt compression and one-command updates. You never pay for models through Ficelle on any plan.
Do my prompts or keys pass through your servers?
No. The router runs on your machine, your API keys stay local, and prompts go straight to the provider you choose. Ficelle-operated servers receive only an optional update request and the Pro license check, which you can disable by setting FICELLE_DISABLE_UPDATE_CHECK=1.
Can it accidentally spend my money?
No. Paid fallback is hardcoded off, not a setting you can toggle, and Ficelle refuses to start if the config claims otherwise. Any model that starts reporting a price is quarantined automatically, and the open core code is public so you can verify it.
Are free models good enough for real work?
For labelling, triage, structured extraction and most reasoning, yes. In a 76-task benchmark against gpt-5, free routing was quality-safe on classification (100%), JSON extraction (95%) and reasoning (94%). Polished long-form writing is the exception, where paid models still win.
Which tools work with it?
Ficelle supports Cursor, Codex, Continue, Open WebUI, LangChain, CrewAI and curl through its OpenAI-compatible endpoint. Claude Code connects natively through Ficelle's Anthropic Messages endpoint, and Hermes and OpenClaw use packaged connectors.

More on this profile

Ficelle has a free listing. The owner can unlock the full profile with a paid launch for $5:

  • Founder story (locked)
  • Milestones (locked)
  • Demo video (locked)
  • Dofollow website link (locked)

Also on the frontier

  1. UberLLM logo

    Rank 1: UberLLM

    One API key for AI models, usually below list price

    LLM APIs & modelsUnited States

    DR 5 no change since last check 0 votes. Log in to send UberLLM a vote
  2. Continuous Intelligence logo

    Rank 2: Continuous Intelligence

    Stream-native AI for real-world time series data

    LLM APIs & modelsStartupUnited Kingdom

    DR 2 no change since last check 0 votes. Log in to send Continuous Intelligence a vote
  3. OpenLLM logo

    Rank 3: OpenLLM

    Local LLM routing layer for Claude Code, Codex, and OpenCode

    LLM APIs & modelsStartupUnited States

    DR 25 no change since last check 0 votes. Log in to send OpenLLM a vote
  4. Open Uncensored logo

    Rank 4: Open Uncensored

    OpenRouter for uncensored models

    LLM APIs & models

    DR 3 +1 (up) since last check 0 votes. Log in to send Open Uncensored a vote
Ask a question